llm-functions - GitLite

KO | EN

gitlite — search

#hacktoberfest #ai #llm #golang #nodejs #java #windows #awesome #awesome-list #security #mcp #ios #openai #open-source

llm-functions

(★ 767)

Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

파일 탐색기

최종 버전 다운로드 (.zip)

- - add_agent.md
  - bug_report.md
  - feature_request.md
- - ci.yaml
- - index.yaml
  - README.md
  - tools.sh
  - tools.txt
- - index.yaml
  - README.md
  - tools.js
  - tools.py
  - tools.sh
  - tools.txt
- - index.yaml
  - package.json
  - README.md
  - tools.js
- - index.yaml
  - README.md
  - tools.sh
- - index.yaml
  - README.md
  - tools.sh
- agent.md
- argcfile.md
- environment-variables.md
- tool.md
- - index.js
  - package.json
  - README.md
- - index.js
  - package.json
  - README.md
- build-declarations.js
- build-declarations.py
- build-declarations.sh
- check-deps.sh
- create-tool.sh
- declarations-util.sh
- mcp.sh
- run-agent.js
- run-agent.py
- run-agent.sh
- run-mcp-tool.sh
- run-tool.js
- run-tool.py
- run-tool.sh
- demo_js.js
- demo_py.py
- demo_sh.sh
- execute_command.sh
- execute_js_code.js
- execute_py_code.py
- execute_sql_code.sh
- fetch_url_via_curl.sh
- fetch_url_via_jina.sh
- fs_cat.sh
- fs_ls.sh
- fs_mkdir.sh
- fs_patch.sh
- fs_rm.sh
- fs_write.sh
- get_current_time.sh
- get_current_weather.sh
- search_arxiv.sh
- search_wikipedia.sh
- search_wolframalpha.sh
- send_mail.sh
- send_twilio.sh
- web_search_aichat.sh
- web_search_perplexity.sh
- web_search_tavily.sh
- guard_operation.sh
- guard_path.sh
- patch.awk
.gitignore
Argcfile.sh
LICENSE
README.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/sigoden/llm-functions

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd llm-functions

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Node.js

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Node.js npm 명령어를 쓰려면 Node.js가 설치되어 있어야 합니다. LTS(장기지원) 버전을 추천합니다.

⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.

cd agents/json-viewer

이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.

npm install

package.json에 명시된 라이브러리들을 내려받아 설치합니다.

npm start

개발/실행 서버를 켭니다.

✅ 명령어 실행 후 터미널에 나타나는 주소(보통 http://localhost:3000 형태)를 브라우저에서 열어보세요.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# LLM Functions

This project empowers you to effortlessly build powerful LLM tools and agents using familiar languages like Bash, JavaScript, and Python.

Forget complex integrations, **harness the power of [function calling](https://platform.openai.com/docs/guides/function-calling)** to connect your LLMs directly to custom code and unlock a world of possibilities. Execute system commands, process data, interact with APIs –  the only limit is your imagination.

**Tools Showcase**
![llm-function-tool](https://github.com/user-attachments/assets/40c77413-30ba-4f0f-a2c7-19b042a1b507)

**Agents showcase**
![llm-function-agent](https://github.com/user-attachments/assets/6e380069-8211-4a16-8592-096e909b921d)

## Prerequisites

Make sure you have the following tools installed:

- [argc](https://github.com/sigoden/argc): A bash command-line framework and command runner
- [jq](https://github.com/jqlang/jq): A JSON processor

## Getting Started with [AIChat](https://github.com/sigoden/aichat)

**Currently, AIChat is the only CLI tool that supports `llm-functions`. We look forward to more tools supporting `llm-functions`.**

### 1. Clone the repository

```sh
git clone https://github.com/sigoden/llm-functions
cd llm-functions
```

### 2. Build tools and agents

#### I. Create a `./tools.txt` file with each tool filename on a new line.

```
get_current_weather.sh
execute_command.sh
#execute_py_code.py
```

<details>
<summary>Where is the web_search tool?</summary>
<br>

The `web_search` tool itself doesn't exist directly, Instead, you can choose from a variety of web search tools.

To use one as the `web_search` tool, follow these steps:

1. **Choose a Tool:** Available tools include:
    * `web_search_cohere.sh`
    * `web_search_perplexity.sh`
    * `web_search_tavily.sh`
    * `web_search_vertexai.sh`

2. **Link Your Choice:** Use the `argc` command to link your chosen tool as `web_search`. For example, to use `web_search_perplexity.sh`:

```sh
    $ argc link-web-search web_search_perplexity.sh
    ```

This command creates a symbolic link, making `web_search.sh` point to your selected `web_search_perplexity.sh` tool.

Now there is a `web_search.sh` ready to be added to your `./tools.txt`.

</details>

#### II. Create a `./agents.txt` file with each agent name on a new line.

```
coder
todo
```

#### III. Build `bin` and `functions.json`

```sh
argc build
```

#### IV. Ensure that everything is ready (environment variables, Node/Python dependencies, mcp-bridge server)

```sh
argc check
```

### 3. Link LLM-functions and AIChat

AIChat expects LLM-functions to be placed in AIChat's **functions_dir** so that AIChat can use the tools and agents that LLM-functions provides.

You can symlink this repository directory to AIChat's **functions_dir** with:

```sh
ln -s "$(pwd)" "$(aichat --info | sed -n 's/^functions_dir\s\+//p')"
# OR
argc link-to-aichat
```

Alternatively, you can tell AIChat where the LLM-functions directory is by using an environment variable:

```sh
export AICHAT_FUNCTIONS_DIR="$(pwd)"
```

### 4. Start using the functions

Done! Now you can use the tools and agents with AIChat.

```sh
aichat --role %functions% what is the weather in Paris?
aichat --agent todo list all my todos
```

## Writing Your Own Tools

Building tools for our platform is remarkably straightforward. You can leverage your existing programming knowledge, as tools are essentially just functions written in your preferred language.

LLM Functions automatically generates the JSON declarations for the tools based on **comments**. Refer to `./tools/demo_tool.{sh,js,py}` for examples of how to use comments for autogeneration of declarations.

### Bash

Create a new bashscript in the [./tools/](./tools/) directory (.e.g. `execute_command.sh`).

```sh
#!/usr/bin/env bash
set -e

# @describe Execute the shell command.
# @option --command! The command to execute.

main() {
    eval "$argc_command" >> "$LLM_OUTPUT"
}

eval "$(argc --argc-eval "$0" "$@")"
```

### Javascript

Create a new javascript in the [./tools/](./tools/) directory (.e.g. `execute_js_code.js`).

```js
/**
 * Execute the javascript code in node.js.
 * @typedef {Object} Args
 * @property {string} code - Javascript code to execute, such as `console.log("hello world")`
 * @param {Args} args
 */
exports.run = function ({ code }) {
  eval(code);
}

```

### Python

Create a new python script in the [./tools/](./tools/) directory (e.g. `execute_py_code.py`).

```py
def run(code: str):
    """Execute the python code.
    Args:
        code: Python code to execute, such as `print("hello world")`
    """
    exec(code)

```

## Writing Your Own Agents

Agent = Prompt + Tools (Function Calling) + Documents (RAG), which is equivalent to OpenAI's GPTs.

The agent has the following folder structure:
```
└── agents
    └── myagent
        ├── functions.json                  # JSON declarations for functions (Auto-generated)
        ├── index.yaml                      # Agent definition
        ├── tools.txt                       # Shared tools
        └── tools.{sh,js,py}                # Agent tools 
```

The agent definition file (`index.yaml`) defines crucial aspects of your agent:

```yaml
name: TestAgent                             
description: This is test agent
version: 0.1.0
instructions: You are a test ai agent to ... 
conversation_starters:
  - What can you do?
variables:
  - name: foo
    description: This is a foo
documents:
  - local-file.txt
  - local-dir/
  - https://example.com/remote-file.txt
```

Refer to [./agents/demo](https://github.com/sigoden/llm-functions/tree/main/agents/demo) for examples of how to implement a agent.

## MCP (Model Context Protocol)

- [mcp/server](https://github.com/sigoden/llm-functions/tree/main/mcp/server): Let LLM-Functions tools/agents be used through the Model Context Protocol. 
- [mcp/bridge](https://github.com/sigoden/llm-functions/tree/main/mcp/bridge): Let external MCP tools be used by LLM-Functions.

## Documents

- [Tool Guide](https://github.com/sigoden/llm-functions/blob/main/docs/tool.md)
- [Agent Guide](https://github.com/sigoden/llm-functions/blob/main/docs/agent.md)
- [Argc Commands](https://github.com/sigoden/llm-functions/blob/main/docs/argcfile.md)

## License

The project is under the MIT License, Refer to the [LICENSE](https://github.com/sigoden/llm-functions/blob/main/LICENSE) file for detailed information.